Deep learning based ECG segmentation for delineation of diverse arrhythmias.

Accurate delineation of key waveforms in an ECG is a critical step in extracting relevant features to support the diagnosis and treatment of heart conditions. Although deep learning based methods using segmentation models to locate P, QRS, and T waves have shown promising results, their ability to handle arrhythmias has not been studied in any detail. In this paper we investigate the effect of arrhythmias on delineation quality and develop strategies to improve performance in such cases. We introduce a U-Net-like segmentation model for ECG delineation with a particular focus on diverse arrhythmias. This is followed by a post-processing algorithm which removes noise and automatically determines the boundaries of P, QRS, and T waves. Our model has been trained on a diverse dataset and evaluated against the LUDB and QTDB datasets to show strong performance, with F1-scores exceeding 99% for QRS and T waves, and over 97% for P waves in the LUDB dataset. Furthermore, we assess various models across a wide array of arrhythmias and observe that models with a strong performance on standard benchmarks may still perform poorly on arrhythmias that are underrepresented in these benchmarks, such as tachycardias. We propose solutions to address this discrepancy.

Association between the accumulation of elevated serum γ-glutamyltransferase level and risk of atrial fibrillation: a nationwide cohort study.

Atrial fibrillation (AF) is the most common cardiac arrhythmia. The association between AF and γ-Glutamyltransferase (GGT) was not fully established. This study demonstrated the independent association of cumulative GGT score and AF incidence with the dose-response relationship. Using the Korean National Health Insurance Corporation database, adult subjects who had 4 consecutive annual health examinations from 2009 to 2012 were enrolled. A cumulative GGT score was calculated as the cumulative number of the highest GGT quartile amongst four examinations (0-4 times). A multivariable Cox proportional hazards regression analysis was performed. Among a total of 3,500,847 people included, AF was developed in 27,752 people (0.793%) during a median of 8.0 years of follow up. The incidence rate of AF and adjusted hazard ratio were increased by a stepwise manner in the higher quartile group and cumulative GGT score group. In subgroup analysis, this trend was more prominent in the elderly, people without hypertension, non-obese people, and people without any four comorbidities (diabetes mellitus, hypertension, dyslipidemia, and obesity). Our results suggest multiple accumulation of elevated GGT levels in health examination might be a useful marker for risk stratification of AF development, especially in the elderly and healthy population.

Brachial-ankle pulse wave velocity as a predictor of long-term cardiovascular events in 2174 subjects with type 2 diabetes mellitus: A retrospective cohort study.

The prognostic value of arterial stiffness in patients with diabetes mellitus (DM) remains unclear. The aim of this study was to investigate the association between brachial-ankle pulse wave velocity (baPWV) and the occurrence of cardiovascular events in people with DM. A total of 2714 subjects (mean age, 63.6 years; males, 59.3%) with type 2 DM and without documented cardiovascular disease and stroke were analyzed. The primary end-point of this study was composite cardiovascular events of cardiac death, non-fatal myocardial infarction, coronary revascularization and stroke. There were 118 composite events (4.3%) during a median follow-up period of 3.84 years (interquartile range, 1.60-5.52 years). In multivariable Cox regression analysis, higher baPWV (≥1672 cm/s) was associated with composite events even after controlling for potential confounders (hazard ratio [HR], 2.00; 95% confidence interval [CI], 1.31-3.07; P = .001). Compared to the lowest baPWV tertile, both middle (HR, 1.84; 95% CI, 1.03-3.27; P = .037) and the highest (HR, 2.97; 95% CI, 1.69-5.22; P < .001) tertile of baPWV were associated with increased risk of cardiovascular events in the same multivariable model. In conclusion, the baPWV was associated with cardiovascular events in people with type 2 DM. Considering the simplicity and convenience of baPWV measurement, baPWV may be useful for risk stratification of people with type 2 DM.

Correction to: "Cardiovascular Outcomes Comparison of Dipeptidyl Peptidase-4 Inhibitors Versus Sulfonylurea as Add-on Therapy for Type 2 Diabetes Mellitus: A Meta-Analysis".

OBJECTIVE: Recent studies have raised concerns about the cardiovascular safety of dipeptidyl peptidase-4 (DPP4) inhibitors. We performed a systematic review and meta-analysis to compare the cardiovascular outcomes of sulfonylureas (SUs) versus DPP4 inhibitors in combination with metformin. METHODS: After searching for trials using combination therapy of metformin with an SU or DPP4 inhibitor in PubMed, Cochrane Library, and Embase, 1 prospective observational study and 15 randomized controlled studies were selected. RESULTS: Regarding the primary analysis endpoint, no significant differences were found in the risk of all-cause mortality between SUs and DPP4 inhibitors as add-on therapies to metformin (random-effect relative risk [RR], 1.14; 95% confidence interval [CI], 0.98-1.33; I2=0%; p=0.097). Cardiovascular death was also similar between SUs and DPP4 inhibitors in the 5 studies that reported outcomes (random-effect RR, 1.03; 95% CI, 0.83-1.27; I2=0%; p=0.817). Furthermore, there were no significant differences in major adverse cardiac events, coronary heart disease, myocardial infarction, and heart failure. However, the SU group showed a higher risk of ischemic stroke, more hypoglycemic events, and more weight gain than the DPP4 inhibitor group (ischemic stroke, random-effect RR, 2.78; 95% CI, 1.06-7.30; I2=51.9%; p=0.039; hypoglycemia, random-effect RR, 3.79; 95% CI, 1.53-9.39; I2=98.2; p=0.004; weight gain, weighted mean difference, 1.68; 95% CI, 1.07-2.29; I2=94.7; p<0.001). CONCLUSION: As add-on therapies to metformin, SUs and DPP4 inhibitors showed no significant differences in all-cause mortality and cardiovascular mortality. However, some of the favorable results of DPP4 inhibitors suggest good safety and feasibility of the drugs.

Cardiovascular Outcomes Comparison of Dipeptidyl Peptidase-4 Inhibitors versus Sulfonylurea as Add-on Therapy for Type 2 Diabetes Mellitus: a Meta-Analysis.

OBJECTIVE: Recent studies have raised concern about the cardiovascular safety of dipeptidyl peptidase-4 (DPP4) inhibitors. We performed a systematic review through meta-analysis to compare cardiovascular outcomes of sulfonylurea (SU) versus DPP4 inhibitors when used in combination with metformin. METHODS: After searching for trials using combination therapy of metformin with DPP4 inhibitor or SU in PubMed, Cochrane Library, and Embase, one prospective observation study and 15 randomized controlled studies were selected. RESULTS: Regarding the primary analysis endpoint, there were no significant differences in the risk of all-cause mortality between SU and DPP4 inhibitors as an add-on therapy to metformin (random-effect relative risk [RR], 1.14; 95% confidence interval [CI], 0.98-1.33; p=0.811; I2=0%). Cardiovascular death was also similar between the two drug classes in the five studies which reported outcomes (random-effect RR, 1.03; 95% CI, 0.83-1.27; p=0.517; I2=0%). Furthermore, there were no significant differences in major adverse cardiac events (MACE), coronary heart disease, myocardial infarction, ischemic stroke and heart failure. However, there were less hypoglycemic events and weight gain in the DPP4 inhibitor group as compared with the SU group (random-effect RR, 3.79; 95% CI, 1.53-9.39; p<0.001; I2=98.2 and weighted mean difference, 1.68; 95% CI, 1.07-2.29; p<0.001; I2=94.7, respectively). CONCLUSION: As add-on therapy to metformin, there were no significant differences in all-cause mortality and cardiovascular mortality between DPP4 inhibitors and SUs.

Anatomical attributes of clinically relevant diagonal branches in patients with left anterior descending coronary artery bifurcation lesions.

AIMS: This study aimed to investigate the anatomical attributes determining myocardial territory of diagonal branches and to develop prediction models for clinically relevant branches using myocardial perfusion imaging (MPI) and coronary CT angiography (CCTA). METHODS AND RESULTS: The amount of ischaemia and subtended myocardial mass of diagonal branches was quantified using MPI by percent ischaemic myocardium (%ischaemia) and CCTA by percent fractional myocardial mass (%FMM), respectively. In 49 patients with isolated diagonal branch disease, the mean %ischaemia by MPI was 6.8±4.0%, whereas in patients with total occlusion or severe disease of all diagonal branches it was 8.4±3.3%. %ischaemia was different according to the presence of non-diseased diagonal branches and dominant left circumflex artery (LCx). In the CCTA cohort (306 patients, 564 diagonal branches), mean %FMM was 5.9±4.4% and 86 branches (15.2%) had %FMM ≥10%. %FMM was different according to LCx dominance, number of branches, vessel size, and relative dominance between two diagonal branches. The diagnostic accuracy of prediction models for %FMM ≥10% based on logistic regression and decision tree was 0.92 (95% CI: 0.85-0.96) and 0.91 (95% CI: 0.84-0.96), respectively. There was no difference in the diagnostic performance of models with and without size criterion. CONCLUSIONS: LCx dominance, number of branches, vessel size, and dominance among diagonal branches determined the myocardial territory of diagonal branches. Clinical application of prediction models based on these anatomical attributes can help to determine the clinically relevant diagonal branches in the cardiac catheterisation laboratory. CLINICAL TRIAL REGISTRATION: NCT03935542

Gender Related Association between Arterial Stiffness and Aortic Root Geometry.

BACKGROUND: The gender-related change in aortic morphology by arterial stiffness has not been well studied. This study was performed to investigate the association between brachial-ankle pulse wave velocity (baPWV) and aortic root size according to gender. METHODS: A total of 263 consecutive subjects (63.2 ± 10.6 years, 71.1% men) without overt cardiovascular disease who underwent both baPWV measurement and transthoracic echocardiography on the same day were retrospectively analyzed. The diameters of the aortic annulus (AN), sinus of Valsalva (SV), sinotubular junction (STJ), and ascending aorta (AA) were measured using 2-dimensional echocardiography. RESULTS: The body surface area (BSA)-corrected diameters of AN, SV, STJ, and AA were significantly higher in women than in men. Univariable analyses showed that baPWV was significantly correlated with SV/BSA and STJ/BSA in men, and with SV/BSA, STJ/BSA, and AA/BSA in women (p < 0.05 for each). In men, however, these associations disappeared in multiple linear regression models after controlling for potential confounders (p > 0.05 for each). In women, the associations of baPWV with diameters of STJ/BSA (ß = 0.407, p < 0.001) and AA/BSA (ß = 0.391, p = 0.005) remained significant in the same multivariate models. Women-specific correlation between aortic root size and baPWV was also similarly demonstrated in age-matched analyses (n = 61 in each gender). CONCLUSIONS: Among Korean adult without overt cardiovascular disease, the association between increased arterial stiffness and aortic root dilatation is stronger in women than in men.

Association between aortic knob width and invasively measured aortic pulse pressure.

BACKGROUND: Aortic knob width (AKW), which can be measured easily in simple radiography, is associated with the degree of dilatation and tortuosity of the aortic arch. Pulsatile stress influences aortic geometry. This study was carried out to investigate whether AKW can represent invasively measured aortic pulse pressure (APP). METHODS: A total of 252 patients who underwent invasive coronary angiography (ICA) for the evaluation of coronary artery disease were enrolled. AKW was defined as the perpendicular length from the lateral margin of the main bronchus to the most prominent edge of the aortic knob on chest radiography. APP was measured at the ascending aorta using a pigtail catheter immediately before ICA. RESULTS: When patients were divided into two groups according to the median value of APP (69 mmHg), AKW was significantly greater in patients with higher APP (≥69 mmHg) than in those with lower APP (<69 mmHg) (40.6±4.9 vs. 38.1±4.2 mm, P<0.001). There was a positive linear correlation between APP and AKW (r=0.207, P<0.001). In multiple linear regression analysis, the significant association between APP and AKW remained even after controlling for the confounding factors, including age, sex, height, heart rate, smoking status, left ventricular ejection fraction, and left ventricular end-diastolic dimension (ß=0.131, P=0.031). CONCLUSION: Greater AKW on chest radiography was independently predictive of increased APP in patients undergoing elective ICA. The results of this study suggest that AKW can be useful as a simple surrogate marker of APP.